The present disclosure relates to a power management method and apparatus, a computing device, a medium, and a product. The power management method includes a monitoring step, a prediction step, an error calculation step and an adjustment step including adjusting power supply plan or a power demand of a user when at least one of a first error is greater than a first predetermined threshold or a second error is greater than a second predetermined threshold.
Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
4. The power management method according to claim 3, wherein the first time period is one month, and the second time period is one day.
5. The power management method according to claim 3, wherein the first prediction model is a first machine learning model obtained by training using power consumption historical data of the first time period as training data, and the second prediction model is a second machine learning model obtained by training using power consumption historical data of the second time period as training data.
6. The power management method according to claim 2, wherein the first time period is one month, and the second time period is one day.
This invention relates to power management systems for optimizing energy consumption in electronic devices. The problem addressed is the need for efficient power management to reduce energy waste while maintaining device functionality. The method involves monitoring power consumption patterns over different time intervals to adjust power settings dynamically. The system first collects power usage data over a first time period, such as one month, to establish baseline consumption trends. This long-term data helps identify recurring usage patterns, such as peak and off-peak hours. Then, the system analyzes power consumption over a shorter second time period, such as one day, to detect immediate fluctuations or anomalies. By comparing these two datasets, the system can distinguish between temporary spikes and consistent usage trends. Based on this analysis, the power management system adjusts power settings to optimize efficiency. For example, it may reduce power during low-usage periods or allocate resources more effectively during high-demand times. The method ensures that power adjustments are both responsive to short-term needs and aligned with long-term usage habits, minimizing unnecessary energy consumption while maintaining performance. This approach is particularly useful for devices with variable power demands, such as smart home systems or industrial equipment.
7. The power management method according to claim 2, wherein the first prediction model is a first machine learning model obtained by training using power consumption historical data of the first time period as training data, and the second prediction model is a second machine learning model obtained by training using power consumption historical data of the second time period as training data.
This invention relates to power management systems that use machine learning models to predict and optimize power consumption. The problem addressed is the need for accurate power consumption forecasting to improve energy efficiency and reduce costs. Traditional methods often fail to account for varying usage patterns across different time periods, leading to suboptimal power management. The invention involves a power management method that employs two distinct machine learning models. The first model is trained using historical power consumption data from a first time period, while the second model is trained using data from a second time period. These models are used to predict power consumption for their respective time periods, allowing for more precise forecasting. The method leverages the fact that power consumption patterns can differ significantly between different times, such as peak and off-peak hours, or seasonal variations. By training separate models on distinct datasets, the system can better adapt to these variations and improve prediction accuracy. The use of machine learning models enables the system to learn from historical data and refine its predictions over time. The models can be updated periodically with new data to maintain accuracy. This approach ensures that power management decisions are based on the most relevant and up-to-date consumption patterns, leading to more efficient energy use and cost savings. The invention is particularly useful in industrial, commercial, and residential settings where power consumption varies significantly across different times.
8. The power management method according to claim 1, wherein the first time period is one month, and the second time period is one day.
A power management method is designed to optimize energy consumption in electronic devices by dynamically adjusting power states based on usage patterns. The method monitors device activity over a first time period, such as one month, to establish a baseline of usage trends. It then analyzes activity within a second, shorter time period, such as one day, to detect deviations from the baseline. If significant deviations are identified, the method adjusts power states to conserve energy when the device is inactive or to enhance performance when demand is high. The method may also incorporate historical data to refine predictions and improve efficiency. By differentiating between long-term and short-term usage patterns, the system ensures adaptive power management that balances energy savings with performance needs. This approach is particularly useful for devices with variable workloads, such as smartphones, laptops, or IoT devices, where power efficiency is critical. The method reduces unnecessary energy consumption during idle periods while maintaining responsiveness during active use.
9. The power management method according to claim 1, wherein the first prediction model is a first machine learning model obtained by training using power consumption historical data of the first time period as training data, and the second prediction model is a second machine learning model obtained by training using power consumption historical data of the second time period as training data.
11. A non-transitory machine readable storage medium storing an executable instruction that, when executed, causes a machine to perform the method according to claim 1.
A system and method for automated data processing involves analyzing input data to identify patterns or anomalies. The system receives input data from one or more sources, such as sensors, databases, or user inputs. The data is processed using machine learning algorithms to detect patterns, trends, or deviations from expected behavior. The system then generates output data based on the analysis, which may include alerts, reports, or recommendations. The output data can be transmitted to a user interface, a storage system, or another processing system for further action. The system may also include a feedback mechanism to refine the analysis over time based on user input or additional data. The machine learning algorithms can be trained using historical data to improve accuracy and adapt to changing conditions. The system is designed to operate in real-time or near-real-time, allowing for timely decision-making. The storage medium contains executable instructions that, when executed by a machine, perform the data processing method. The system is applicable in various domains, such as industrial monitoring, financial analysis, or healthcare diagnostics, where automated data analysis is critical for identifying issues or opportunities.
15. The power management apparatus according to claim 13, wherein the first time period is one month, and the second time period is one day.
16. The power management apparatus according to claim 13, wherein the first prediction model is a first machine learning model obtained through training using power consumption historical data of the first time period as training data, and the second prediction model is a second machine learning model obtained through training using power consumption historical data of the second time period as training data.
17. The power management apparatus according to claim 12, wherein the first time period is one month, and the second time period is one day.
A power management apparatus is designed to optimize energy consumption in a system by dynamically adjusting power states based on usage patterns. The apparatus monitors power consumption over a first time period, such as one month, to establish long-term usage trends. It also tracks consumption over a second, shorter time period, such as one day, to detect immediate fluctuations. By analyzing these intervals, the apparatus identifies periods of high and low activity, allowing it to transition between active and low-power states efficiently. This dual-timeframe approach ensures that the system conserves energy during idle periods while maintaining responsiveness during peak usage. The apparatus may also incorporate additional features, such as predictive algorithms to anticipate future power demands and adaptive thresholds to fine-tune power state transitions. The goal is to reduce energy waste without compromising system performance, making it suitable for applications in data centers, consumer electronics, or industrial equipment where power efficiency is critical. The apparatus may be integrated into existing power management systems or operate as a standalone controller, depending on the implementation.
18. The power management apparatus according to claim 12, wherein the first prediction model is a first machine learning model obtained through training using power consumption historical data of the first time period as training data, and the second prediction model is a second machine learning model obtained through training using power consumption historical data of the second time period as training data.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
May 22, 2019
November 15, 2022
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.